README.md

---
tags:
- unsloth
- mlx
- mlx-my-repo
base_model: unsloth/Qwen3-Coder-30B-A3B-Instruct
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
---

# huggingtoots/unsloth-Qwen3-Coder-30B-A3B-Instruct-mlx-8Bit

The Model [huggingtoots/unsloth-Qwen3-Coder-30B-A3B-Instruct-mlx-8Bit](https://huggingface.co/huggingtoots/unsloth-Qwen3-Coder-30B-A3B-Instruct-mlx-8Bit) was converted to MLX format from [unsloth/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct) using mlx-lm version **0.26.4**.

## Toots' Note:
This model was converted and quantized utilizing unsloth's version of Qwen3-Coder-30B-A3B-Instruct. Should include the chat template fixes.

Please follow and support [unsloth's work](https://huggingface.co/unsloth) if you like it!

🦛 <span style="color:#800080">If you want a free consulting session, </span>[fill out this form](https://forms.gle/xM9gw1urhypC4bWS6) <span style="color:#800080">to get in touch!</span> 🤗




## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("huggingtoots/Qwen3-Coder-30B-A3B-Instruct-mlx-8Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```